Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    casts
    -0.06
     푸
    -0.06
     ledna
    -0.06
    Arn
    -0.06
     SCT
    -0.06
    >n
    -0.06
     cst
    -0.05
    edin
    -0.05
    .writ
    -0.05
    、い
    -0.05
    POSITIVE LOGITS
     сез
    0.07
     paragraphs
    0.07
    ième
    0.07
     Objects
    0.06
    -command
    0.06
     فرمود
    0.06
     inherits
    0.06
    :first
    0.06
     Chambers
    0.06
    ونه
    0.06
    Act Density 0.011%

    No Known Activations